Introduces DF framework for sampling decisions from target distributions.
problem Sampling from target distributions with additional guidance.
method DF framework based on MDP and Path Integral Diffusion.
result DF enhances guided sampling across various applications.
GEAR uses auxiliary data to estimate optimal decisions in studies with limited primary outcomes.
problem Estimating optimal decisions when primary outcomes are not available in experimental samples.
method GEAR uses augmented inverse propensity weighting to estimate optimal decisions based on auxiliary data.
result GEAR estimators and value estimators have established asymptotic properties and are validated in simulations and a real application.
PDTS improves robustness in sequential decision-making.
problem Robust active task sampling for efficient and reliable decision-making.
method Characterizes robust active task sampling as a Markov decision process, proposes PDTS method.
result Significantly improves zero-shot and few-shot adaptation robustness.
Improves generative models for cost-sensitive decisions.
problem Generative models lack awareness of decision costs.
method Integrates a decision loss into the training objective.
result Improves cost-sensitive forecast accuracy.
Geometric methods solve sampling, optimisation, inference, and adaptive decision-making.
problem Efficient solutions for sampling, optimisation, inference, and adaptive decision-making.
method Derive algorithms exploiting geometric structures of Hamiltonian systems, Hilbertian subspaces, and information geometry.
result Wide range of geometric theories emerge in these fields, enabling efficient solutions.
New algorithms achieve decision calibration without sample complexity dependent on feature dimension.
problem Achieving decision calibration for nonlinear loss functions with polynomial sample complexity.
method Developed smooth relaxation of decision calibration, enabling dimension-free algorithms.
result Efficient algorithms post-process predictors to satisfy decision calibration without worsening accuracy.
Many decision problems in science, engineering and economics are affected by uncertain parameters whose distribution is only indirectly observable through samples. The goal of data-driven decision-making is to learn a decision from finitely many training samples that will perform well on unseen test samples. This learn…
Generative model simulates rare events for better decision making.
problem Rare events impact decision making but are hard to sample.
method Normalizing Flow coupled with Importance Sampling.
result Accurate estimation of rare events improves decision outcomes.
Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is still an open problem. In this paper, we provide a new perspective based on a decision boundary, which…
New method combines multiple data sources for optimal decision-making with limited outcomes.
problem Optimal decision-making with limited outcome data from multiple heterogeneous sources.
method Calibrated optimal decision-making method leveraging common intermediate outcomes.
result Proposed estimator of conditional mean outcome is asymptotically normal and more efficient.
DAT-CGAN improves time series generation for better decision support.
problem Generating accurate time series data for decision support.
method DAT-CGAN uses multi-Wasserstein loss and overlapped block-sampling for improved sample efficiency.
result DAT-CGAN outperforms GAN-based baselines in generating data relevant to decision processes.
New algorithms for fast online decision making using neural networks and martingale posteriors.
problem Online sequential decision making under uncertainty.
method Martingale posterior neural networks for fast online learning and decision making.
result Achieves competitive performance-speed trade-offs in non-stationary contextual bandits and Bayesian optimization.
New active learning strategy improves decision-making accuracy.
problem Maximizing decision-making accuracy in sequential data acquisition.
method Introduces a novel active learning criterion that maximizes expected information gain on the posterior decision distribution.
result Improved performance in decision-making accuracy compared to existing alternatives.
Off-policy policy estimators that use importance sampling (IS) can suffer from high variance in long-horizon domains, and there has been particular excitement over new IS methods that leverage the structure of Markov decision processes. We analyze the variance of the most popular approaches through the viewpoint of con…
IDT learns human preferences from uncertain decisions, even when humans are suboptimal.
problem Learning human preferences from uncertain and suboptimal decisions.
method Inverse decision theory (IDT) framework, statistical analysis of IDT, characterizing sample complexity.
result Learning preferences is easier when decisions are more uncertain, even if humans are suboptimal.
Batch Thompson Sampling reduces exploration-exploitation trade-off in online decision making.
problem Balancing exploration and exploitation in online decision making.
method Introducing a batch Thompson Sampling framework for stochastic multi-arm bandit and linear contextual bandit problems.
result Achieves asymptotic regret bound with O ( log T ) O(\log T) O ( log T ) batch queries, significantly reducing interactions. A new nonparametric test measures dependence between variables using decision trees.
problem Measuring statistical dependence between two variables robustly and efficiently.
method An ensemble of decision trees discriminates between observed and permuted samples without generating the latter.
result The method effectively detects complex relationships from noisy data.
Paper introduces a new method for improving reinforcement learning performance using transfer learning.
problem Improving reinforcement learning performance with limited sample sizes in dynamic decision-making scenarios.
method Developed a novel ``re-weighted targeting procedure'' and ``transfer deep Q ∗ Q^* Q ∗ -learning'' approach. result Demonstrated improved reinforcement learning performance through strategic sample construction.
Bayesian framework for learning optimal action-value function in MDPs.
problem Uncertainty quantification in MDPs for optimal decision-making strategies.
method Full Bayesian framework including modelling, inference, and decision-making.
result Demonstrates exploration benefits of posterior sampling in MDPs.
New DEC variant improves sample complexity bounds in decision making.
problem Understanding sample-efficient learning guarantees in decision making.
method Introducing a new Constrained Decision-Estimation Coefficient (DEC) and using it to derive improved lower bounds.
result New lower bounds improve upon prior work in three aspects: expectation, global applicability, and improper reference models.
Efficiently selects top-m designs for various contexts using sequential sampling.
problem Optimizing selection of top-m designs across different contexts.
method Formulated as a stochastic dynamic programming problem, developed sequential sampling policy.
result Asymptotically optimal sampling ratios for efficient selection.
New attacks reveal membership in label-only ML models.
problem Vulnerability of ML models to membership inference attacks.
method Developed decision-based membership inference attacks.
result Label-only exposures are vulnerable to membership leakage.
TS-Insight visualizes Thompson Sampling for better debugging and trust.
problem Thompson Sampling's black box nature hinders debugging and trust.
method TS-Insight is a visual analytics tool that traces evolving posteriors and evidence counts.
result Visualizations help in verifying, diagnosing, and explaining Thompson Sampling dynamics.
MCCE generates realistic counterfactual explanations for tabular data.
problem Creating valid and actionable counterfactual explanations for complex tabular data.
method MCCE models the joint distribution of features and decision using an autoregressive generative model with decision trees. It samples counterfactuals and removes invalid ones.
result MCCE outperforms state-of-the-art methods on various performance metrics and is faster.
Two new approaches improve decision-making in asset monitoring systems.
problem Sampling bias in risk-based active learning leads to poor performance later.
method Semi-supervised learning and discriminative classification models.
result Discriminative classifiers are more robust to sampling bias.
Improved reasoning model by sampling from power distribution without additional training.
problem Efficiently sampling from a sharpened distribution to improve reasoning models.
method Entropy-Cut Metropolis-Hastings algorithm that identifies key decision points for resampling.
result The method consistently improves reasoning models across various datasets.
New approach calibrates predictions for better decision-making.
problem Achieving reliable predictions for multi-class problems is hard.
method Introduces decision calibration, a new approach to calibrate predictions.
result Designs a recalibration algorithm that makes predictions reliable for decision-making.
New algorithm reduces sample complexity for planning in MDPs.
problem Planning in MDPs with unknown transitions.
method MDP-GapE, a trajectory-based MCTS algorithm.
result Proves upper bound on sample complexity in terms of sub-optimality gaps.
The paper addresses sampling bias in risk-based active learning.
problem Sampling bias in active learning leads to poor decision-making performance.
method The paper uses a semi-supervised Gaussian mixture model with an EM algorithm to counteract sampling bias.
result The EM algorithm effectively incorporates pseudo-labels for unlabelled data, reducing sampling bias.
Deep imagination optimizes decision-making in large trees with limited resources.
problem Optimal planning in large decision trees with limited resources and time.
method Analytical solutions and numerical analysis of sampling capacity allocation.
result Optimal policy is to allocate few samples per level for deep exploration, favoring depth over breadth.
Enhanced decision-making through Dreamer's anticipatory trajectories and Online Decision Transformer.
problem Efficiently integrating world models with decision transformers.
method Combining Dreamer's trajectory forecasting with Online Decision Transformer's adaptive learning.
result Notable improvements in sample efficiency and reward maximization.
RAPID efficiently samples SVDD subsets for better anomaly detection.
problem Efficiently sampling SVDD subsets for large datasets.
method Formulated as an optimization problem, RAPID selects samples that approximate the full SVDD decision boundary.
result RAPID outperforms competitors in classification accuracy, sample size, and runtime.
New batched Langevin Thompson Sampling reduces communication costs for sequential decision making.
problem Efficiently learning unknown reward distributions and transition dynamics in batched settings.
method Langevin Thompson Sampling with logarithmic communication costs.
result Order-optimal regret guarantees for stochastic MABs and RL.
New Q-learning method achieves optimal sample complexity for average-reward problems.
problem Challenges in achieving optimal sample complexity for average-reward Q-learning.
method Synchronous and asynchronous Q-learning with a new contraction principle.
result Optimal O ~ ( ε − 2 ) \widetilde{O}(\varepsilon^{-2}) O ( ε − 2 ) sample complexity guarantees. Mixup reduces the sample complexity of finding optimal decision boundaries for more separable data.
problem Finding optimal decision boundaries in separable data distributions.
method Mixup technique applied to binary linear classification problems.
result Mixup significantly reduces the sample complexity for more separable data.
New complexity measure for interactive learning reduces regret to near-optimal levels.
problem Challenges in sample-efficient, adaptive learning algorithms for interactive decision making.
method Introduces the Decision-Estimation Coefficient and the Estimation-to-Decisions (E2D) principle.
result Unified algorithm design principle E2D achieves optimal sample-efficient learning.
The paper calculates how much data is needed to learn decision lists in the presence of evasion attacks.
problem Quantifying sample complexity for robust learning of decision lists against evasion attacks.
method PAC learning framework, Lipschitz condition on distributions, lower and upper bounds on sample complexity.
result Upper and lower bounds on sample complexity for robust learning of decision lists, showing exponential vs polynomial dependence on adversary's budget.
In data-limited settings, stochastic policies can outperform deterministic ones in bandit problems.
problem Making reliable decisions with limited data in bandit problems.
method Designing TRUST, an algorithm that uses localization laws and relative pessimism.
result TRUST achieves comparable sample complexity to LCB on minimax problems but is significantly lower on few-sample problems.
Optimizes decisions without knowing the true distribution using historical data.
problem Optimizing decisions without knowing the true distribution.
method Combines sampling and bisection search algorithms to solve an optimization problem.
result Proves sufficient conditions for local out-of-sample optimality.
New framework calibrates decision robustness using inverse conformal risk control.
problem Inadequate robustness levels in decision-making due to ad hoc choices.
method Constructs valid estimators to trace miscoverage-regret Pareto frontier.
result Provides distribution-free, finite-sample guarantees on robustness levels.
Study on multi-agent decision making complexity, showing sample efficiency gaps.
problem Understanding sample efficiency in multi-agent decision making.
method General framework for interactive decision making, focusing on equilibrium computation.
result No 'reasonable' complexity measure can close gaps between single and multiple agents.
DR-MCTS improves decision quality and sample efficiency in complex environments.
problem Improving decision quality and sample efficiency in complex environments.
method Integrates Doubly Robust off-policy estimation into Monte Carlo Tree Search (MCTS).
result DR-MCTS achieves superior performance in Tic-Tac-Toe and VirtualHome tasks.
Optimal sparse recovery with decision stumps achieves strong feature selection guarantees.
problem Sparse recovery of active features from high-dimensional data.
method Analysis of single-depth decision trees (decision stumps) for feature selection in linear regression.
result Tight sample performance guarantees for O ( s log p ) O(s \log p) O ( s log p ) , improving upon previous bounds. ACE improves counterfactual explanations with fewer model queries.
problem Inefficient sampling for counterfactual explanations in machine learning models.
method Adaptive sampling combining Bayesian estimation and stochastic optimization.
result ACE achieves superior evaluation efficiency compared to state-of-the-art methods.
A new classifier improves one-class predictions on unevenly sampled data.
problem Non-uniformly sampled data affects one-class classifier performance.
method Dynamic decision boundary based on minimum spanning tree.
result Proves effectiveness and robustness compared to state-of-the-art classifiers.
The paper emphasizes the importance of joint predictions over marginal predictions for decision-making.
problem The need for accurate joint predictions in decision-making problems.
method The paper analyzes combinatorial decision problems, sequential predictions, and multi-armed bandits, introducing an approximate Thompson sampling algorithm and new regret bounds.
result Accurate joint predictions are essential for good performance in decision-making problems.
Develops robust MDPs for unknown disturbances with performance guarantees.
problem Unknown disturbance distribution in MDPs.
method Empirical distribution, sublevel set of distance function, weak convergence, concentration inequality.
result Robust optimal value function converges to true optimal value function with increasing sample sizes.
A new method for decision-focused learning using diffusion models.
problem Inability of deterministic point predictions to capture stochasticity in real-world environments.
method Proposes a diffusion-based DFL approach that trains a diffusion model to represent uncertain parameters and optimizes decisions through stochastic optimization.
result Empirically shows consistent outperformance over strong baselines in decision quality.